Axel Meineke1, Christian Rubbert2, Lino M Sawicki3, Christoph Thomas3, Yan Klosterkemper3, Elisabeth Appel3, Julian Caspers3,4, Oliver T Bethge3, Patric Kröpil3, Gerald Antoch3, Johannes Boos3. 1. Cerner HS Deutschland GmbH, 13629, Berlin, Germany. 2. Department of Diagnostic and Interventional Radiology, Medical Faculty, University Dusseldorf, 40225, Dusseldorf, Germany. christian.rubbert@med.uni-duesseldorf.de. 3. Department of Diagnostic and Interventional Radiology, Medical Faculty, University Dusseldorf, 40225, Dusseldorf, Germany. 4. Research Centre Jülich, Institute of Neuroscience and Medicine (INM-1), 52425, Jülich, Germany.
Abstract
OBJECTIVES: To evaluate machine learning (ML) to detect chest CT examinations with dose optimization potential for quality assurance in a retrospective, cross-sectional study. METHODS: Three thousand one hundred ninety-nine CT chest examinations were used for training and testing of the feed-forward, single hidden layer neural network (January 2016-December 2017, 60% male, 62 ± 15 years, 80/20 split). The model was optimized and trained to predict the volumetric computed tomography dose index (CTDIvol) based on scan patient metrics (scanner, study description, protocol, patient age, sex, and water-equivalent diameter (DW)). The root mean-squared error (RMSE) was calculated as performance measurement. One hundred separate, consecutive chest CTs were used for validation (January 2018, 60% male, 63 ± 16 years), independently reviewed by two blinded radiologists with regard to dose optimization, and used to define an optimal cutoff for the model. RESULTS: RMSE was 1.71, 1.45, and 1.52 for the training, test, and validation dataset, respectively. The scanner and DW were the most important features. The radiologists found dose optimization potential in 7/100 of the validation cases. A percentage deviation of 18.3% between predicted and actual CTDIvol was found to be the optimal cutoff: 8/100 cases were flagged as suboptimal by the model (range 18.3-53.2%). All of the cases found by the radiologists were identified. One examination was flagged only by the model. CONCLUSIONS: ML can comprehensively detect CT examinations with dose optimization potential. It may be a helpful tool to simplify CT quality assurance. CT scanner and DW were most important. Final human review remains necessary. A threshold of 18.3% between the predicted and actual CTDIvol seems adequate for CT quality assurance. KEY POINTS: • Machine learning can be integrated into CT quality assurance to improve retrospective analysis of CT dose data. • Machine learning may help to comprehensively detect dose optimization potential in chest CT, but an individual review of the results by an experienced radiologist or radiation physicist is required to exclude false-positive findings.
OBJECTIVES: To evaluate machine learning (ML) to detect chest CT examinations with dose optimization potential for quality assurance in a retrospective, cross-sectional study. METHODS: Three thousand one hundred ninety-nine CT chest examinations were used for training and testing of the feed-forward, single hidden layer neural network (January 2016-December 2017, 60% male, 62 ± 15 years, 80/20 split). The model was optimized and trained to predict the volumetric computed tomography dose index (CTDIvol) based on scan patient metrics (scanner, study description, protocol, patient age, sex, and water-equivalent diameter (DW)). The root mean-squared error (RMSE) was calculated as performance measurement. One hundred separate, consecutive chest CTs were used for validation (January 2018, 60% male, 63 ± 16 years), independently reviewed by two blinded radiologists with regard to dose optimization, and used to define an optimal cutoff for the model. RESULTS: RMSE was 1.71, 1.45, and 1.52 for the training, test, and validation dataset, respectively. The scanner and DW were the most important features. The radiologists found dose optimization potential in 7/100 of the validation cases. A percentage deviation of 18.3% between predicted and actual CTDIvol was found to be the optimal cutoff: 8/100 cases were flagged as suboptimal by the model (range 18.3-53.2%). All of the cases found by the radiologists were identified. One examination was flagged only by the model. CONCLUSIONS:ML can comprehensively detect CT examinations with dose optimization potential. It may be a helpful tool to simplify CT quality assurance. CT scanner and DW were most important. Final human review remains necessary. A threshold of 18.3% between the predicted and actual CTDIvol seems adequate for CT quality assurance. KEY POINTS: • Machine learning can be integrated into CT quality assurance to improve retrospective analysis of CT dose data. • Machine learning may help to comprehensively detect dose optimization potential in chest CT, but an individual review of the results by an experienced radiologist or radiation physicist is required to exclude false-positive findings.
Authors: Hub Boere; Nienke G Eijsvoogel; Anna M Sailer; Joachim E Wildberger; Michiel W de Haan; Marco Das; Cecile R L P N Jeukens Journal: AJR Am J Roentgenol Date: 2018-03-23 Impact factor: 3.959
Authors: Johannes Boos; Patric Kröpil; Oliver Th Bethge; Joel Aissa; Christoph Schleich; Lino Morris Sawicki; Niklas Heinzler; Gerald Antoch; Christoph Thomas Journal: Radiat Prot Dosimetry Date: 2018-01-01 Impact factor: 0.972
Authors: T Küstner; S Gatidis; A Liebgott; M Schwartz; L Mauch; P Martirosian; H Schmidt; N F Schwenzer; K Nikolaou; F Bamberg; B Yang; F Schick Journal: Magn Reson Imaging Date: 2018-07-21 Impact factor: 2.546
Authors: Yan Klosterkemper; Elisabeth Appel; Christoph Thomas; Oliver T Bethge; Joel Aissa; Patric Kröpil; Gerald Antoch; Johannes Boos Journal: Acad Radiol Date: 2018-03-23 Impact factor: 3.173
Authors: Xiao Chen; Qingshan Deng; Qiang Wang; Xinmiao Liu; Lei Chen; Jinjin Liu; Shuangquan Li; Meihao Wang; Guoquan Cao Journal: Front Public Health Date: 2022-04-26
Authors: H O Tekin; Faisal Almisned; T T Erguzel; Mohamed M Abuzaid; W Elshami; Antoaneta Ene; Shams A M Issa; Hesham M H Zakaly Journal: Front Public Health Date: 2022-07-28